Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 274
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-274.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.772.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
1198 3604 4971 5877 5693 5697 2634 2656 3208 6529 4219 4028 1368 5752 1522 4928 
  17   18   19   20   21   22   23   24   25 
2895 2554 3372 2537 4741 3293 2858 3739 5008 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

       fecha_cnt       tmax       tmin  longitud   latitud    altitud
[1,] -0.09845383 -0.7232881 -0.8671244 0.5430281 0.3207037  0.4009103
[2,]  0.85670052  0.1997408  0.2237538 0.2286185 0.2040681 -0.0738962

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud   latitud      tmax      tmin fecha_cnt 
0.9623280 0.9398105 0.9365998 0.9346051 0.9228478 0.9132803 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:126.0   1st Qu.:  29.00   1st Qu.:  6.00  
 Median : 3.000   Median :161.0   Median :  62.00   Median : 14.00  
 Mean   : 3.276   Mean   :157.7   Mean   :  59.53   Mean   : 19.08  
 3rd Qu.: 4.000   3rd Qu.:192.0   3rd Qu.:  91.00   3rd Qu.: 26.00  
 Max.   :12.000   Max.   :307.0   Max.   : 191.00   Max.   :371.00  
     nevada           prof_nieve         longitud        latitud      
 Min.   :0.000000   Min.   :   0.00   Min.   :35.28   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.:   0.00   1st Qu.:38.99   1st Qu.:-4.850  
 Median :0.000000   Median :   0.00   Median :41.10   Median :-2.483  
 Mean   :0.000499   Mean   :   1.13   Mean   :40.59   Mean   :-2.354  
 3rd Qu.:0.000000   3rd Qu.:   0.00   3rd Qu.:42.29   3rd Qu.: 0.595  
 Max.   :6.000000   Max.   :1834.00   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 261.0  
 Mean   : 478.5  
 3rd Qu.: 687.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   : 4.00   Min.   :  8.0   Min.   :-110.0   Min.   :  0.00  
 1st Qu.: 7.00   1st Qu.:178.0   1st Qu.:  83.0   1st Qu.:  2.00  
 Median : 9.00   Median :240.0   Median : 129.0   Median :  9.00  
 Mean   : 8.95   Mean   :230.3   Mean   : 121.7   Mean   : 15.31  
 3rd Qu.:11.00   3rd Qu.:286.0   3rd Qu.: 165.0   3rd Qu.: 21.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.0   Max.   :422.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.95   Median :-2.7331  
 Mean   :0.0001803   Mean   : 0.02173   Mean   :40.52   Mean   :-2.5168  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4914  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 358.7  
 3rd Qu.: 639.0  
 Max.   :1894.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:132.0   1st Qu.: 33.00   1st Qu.:  5.00  
 Median :3.000   Median :164.0   Median : 64.00   Median : 13.00  
 Mean   :3.006   Mean   :163.5   Mean   : 63.08   Mean   : 17.84  
 3rd Qu.:4.000   3rd Qu.:194.0   3rd Qu.: 92.00   3rd Qu.: 24.00  
 Max.   :8.000   Max.   :307.0   Max.   :191.00   Max.   :371.00  
     nevada          prof_nieve          longitud        latitud       
 Min.   :0.00000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.00000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.4981  
 Median :0.00000   Median : 0.00000   Median :40.96   Median :-2.7331  
 Mean   :0.00054   Mean   : 0.08802   Mean   :40.48   Mean   :-2.5254  
 3rd Qu.:0.00000   3rd Qu.: 0.00000   3rd Qu.:42.14   3rd Qu.: 0.4914  
 Max.   :6.00000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.0  
 Median : 196.0  
 Mean   : 345.1  
 3rd Qu.: 617.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   : 4.00   Min.   :  8.0   Min.   :-110.0   Min.   :  0.00  
 1st Qu.: 7.00   1st Qu.:178.0   1st Qu.:  83.0   1st Qu.:  2.00  
 Median : 9.00   Median :240.0   Median : 129.0   Median :  9.00  
 Mean   : 8.95   Mean   :230.3   Mean   : 121.7   Mean   : 15.31  
 3rd Qu.:11.00   3rd Qu.:286.0   3rd Qu.: 165.0   3rd Qu.: 21.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.0   Max.   :422.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.95   Median :-2.7331  
 Mean   :0.0001803   Mean   : 0.02173   Mean   :40.52   Mean   :-2.5168  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4914  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 358.7  
 3rd Qu.: 639.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.569   Mean   : 87.06   Mean   :  16.29   Mean   : 34.19  
 3rd Qu.:10.000   3rd Qu.:142.00   3rd Qu.:  65.00   3rd Qu.: 46.75  
 Max.   :12.000   Max.   :255.00   Max.   : 146.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.81   Mean   :41.93   Mean   :-0.2669   Mean   :2102  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:132.0   1st Qu.: 33.00   1st Qu.:  5.00  
 Median :3.000   Median :164.0   Median : 64.00   Median : 13.00  
 Mean   :3.006   Mean   :163.5   Mean   : 63.08   Mean   : 17.84  
 3rd Qu.:4.000   3rd Qu.:194.0   3rd Qu.: 92.00   3rd Qu.: 24.00  
 Max.   :8.000   Max.   :307.0   Max.   :191.00   Max.   :371.00  
     nevada          prof_nieve          longitud        latitud       
 Min.   :0.00000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.00000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.4981  
 Median :0.00000   Median : 0.00000   Median :40.96   Median :-2.7331  
 Mean   :0.00054   Mean   : 0.08802   Mean   :40.48   Mean   :-2.5254  
 3rd Qu.:0.00000   3rd Qu.: 0.00000   3rd Qu.:42.14   3rd Qu.: 0.4914  
 Max.   :6.00000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.0  
 Median : 196.0  
 Mean   : 345.1  
 3rd Qu.: 617.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :165.0   Min.   : 54.0   Min.   :  0.0   Min.   :0  
 1st Qu.: 6.000   1st Qu.:251.0   1st Qu.:133.0   1st Qu.:  1.0   1st Qu.:0  
 Median : 7.000   Median :278.0   Median :158.0   Median :  6.0   Median :0  
 Mean   : 7.498   Mean   :277.4   Mean   :157.8   Mean   : 10.7   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:304.0   3rd Qu.:183.0   3rd Qu.: 15.0   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  43.3  
 Median : 0.00000   Median :40.95   Median :-2.9056   Median : 240.0  
 Mean   : 0.00302   Mean   :40.50   Mean   :-2.6288   Mean   : 345.9  
 3rd Qu.: 0.00000   3rd Qu.:42.18   3rd Qu.: 0.4483   3rd Qu.: 627.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.569   Mean   : 87.06   Mean   :  16.29   Mean   : 34.19  
 3rd Qu.:10.000   3rd Qu.:142.00   3rd Qu.:  65.00   3rd Qu.: 46.75  
 Max.   :12.000   Max.   :255.00   Max.   : 146.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.81   Mean   :41.93   Mean   :-0.2669   Mean   :2102  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:129.0   1st Qu.:  40.00   1st Qu.:  6.00  
 Median :11.00   Median :165.0   Median :  73.00   Median : 15.00  
 Mean   :10.98   Mean   :164.3   Mean   :  71.25   Mean   : 21.76  
 3rd Qu.:12.00   3rd Qu.:199.0   3rd Qu.: 101.00   3rd Qu.: 30.00  
 Max.   :12.00   Max.   :284.0   Max.   : 188.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.96   Median :-2.4544  
 Mean   :0.0004325   Mean   : 0.04792   Mean   :40.54   Mean   :-2.3602  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 261.0  
 Mean   : 376.6  
 3rd Qu.: 667.0  
 Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:132.0   1st Qu.: 33.00   1st Qu.:  5.00  
 Median :3.000   Median :164.0   Median : 64.00   Median : 13.00  
 Mean   :3.006   Mean   :163.5   Mean   : 63.08   Mean   : 17.84  
 3rd Qu.:4.000   3rd Qu.:194.0   3rd Qu.: 92.00   3rd Qu.: 24.00  
 Max.   :8.000   Max.   :307.0   Max.   :191.00   Max.   :371.00  
     nevada          prof_nieve          longitud        latitud       
 Min.   :0.00000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.00000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.4981  
 Median :0.00000   Median : 0.00000   Median :40.96   Median :-2.7331  
 Mean   :0.00054   Mean   : 0.08802   Mean   :40.48   Mean   :-2.5254  
 3rd Qu.:0.00000   3rd Qu.: 0.00000   3rd Qu.:42.14   3rd Qu.: 0.4914  
 Max.   :6.00000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.0  
 Median : 196.0  
 Mean   : 345.1  
 3rd Qu.: 617.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :165.0   Min.   : 54.0   Min.   :  0.0   Min.   :0  
 1st Qu.: 6.000   1st Qu.:251.0   1st Qu.:133.0   1st Qu.:  1.0   1st Qu.:0  
 Median : 7.000   Median :278.0   Median :158.0   Median :  6.0   Median :0  
 Mean   : 7.498   Mean   :277.4   Mean   :157.8   Mean   : 10.7   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:304.0   3rd Qu.:183.0   3rd Qu.: 15.0   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  43.3  
 Median : 0.00000   Median :40.95   Median :-2.9056   Median : 240.0  
 Mean   : 0.00302   Mean   :40.50   Mean   :-2.6288   Mean   : 345.9  
 3rd Qu.: 0.00000   3rd Qu.:42.18   3rd Qu.: 0.4483   3rd Qu.: 627.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.569   Mean   : 87.06   Mean   :  16.29   Mean   : 34.19  
 3rd Qu.:10.000   3rd Qu.:142.00   3rd Qu.:  65.00   3rd Qu.: 46.75  
 Max.   :12.000   Max.   :255.00   Max.   : 146.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.81   Mean   :41.93   Mean   :-0.2669   Mean   :2102  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:129.0   1st Qu.:  40.00   1st Qu.:  6.00  
 Median :11.00   Median :165.0   Median :  73.00   Median : 15.00  
 Mean   :10.98   Mean   :164.3   Mean   :  71.25   Mean   : 21.76  
 3rd Qu.:12.00   3rd Qu.:199.0   3rd Qu.: 101.00   3rd Qu.: 30.00  
 Max.   :12.00   Max.   :284.0   Max.   : 188.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.96   Median :-2.4544  
 Mean   :0.0004325   Mean   : 0.04792   Mean   :40.54   Mean   :-2.3602  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 261.0  
 Mean   : 376.6  
 3rd Qu.: 667.0  
 Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt         tmax            tmin            precip      
 Min.   :1.00   Min.   : 69.0   Min.   :-41.00   Min.   :  0.00  
 1st Qu.:2.00   1st Qu.:160.0   1st Qu.: 60.00   1st Qu.:  3.00  
 Median :3.00   Median :184.0   Median : 85.00   Median : 10.00  
 Mean   :3.14   Mean   :187.6   Mean   : 86.01   Mean   : 14.03  
 3rd Qu.:4.00   3rd Qu.:215.0   3rd Qu.:113.00   3rd Qu.: 20.00  
 Max.   :8.00   Max.   :307.0   Max.   :191.00   Max.   :259.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.:-4.8458  
 Median :0.0000000   Median : 0.00000   Median :39.47   Median : 0.3664  
 Mean   :0.0002341   Mean   : 0.02341   Mean   :39.18   Mean   :-1.2081  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.31   3rd Qu.: 1.2008  
 Max.   :2.0000000   Max.   :40.00000   Max.   :43.36   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 19.0  
 Median : 61.0  
 Mean   :114.1  
 3rd Qu.:158.0  
 Max.   :816.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:111.0   1st Qu.: 15.00   1st Qu.:  7.00  
 Median :3.000   Median :141.0   Median : 43.00   Median : 16.00  
 Mean   :2.879   Mean   :140.7   Mean   : 41.42   Mean   : 21.44  
 3rd Qu.:4.000   3rd Qu.:170.0   3rd Qu.: 68.75   3rd Qu.: 29.00  
 Max.   :6.000   Max.   :256.0   Max.   :138.00   Max.   :371.00  
     nevada           prof_nieve         longitud        latitud      
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.66   1st Qu.:-5.649  
 Median :0.000000   Median : 0.0000   Median :41.99   Median :-3.789  
 Mean   :0.000829   Mean   : 0.1491   Mean   :41.71   Mean   :-3.770  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:42.87   3rd Qu.:-2.039  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 263.0  
 Median : 617.0  
 Mean   : 563.3  
 3rd Qu.: 790.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 5.000   Min.   :210.0   Min.   :105.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:272.0   1st Qu.:163.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :290.0   Median :181.0   Median :  3.000   Median :0  
 Mean   : 7.578   Mean   :292.5   Mean   :180.4   Mean   :  8.005   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:311.0   3rd Qu.:198.0   3rd Qu.: 11.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve    longitud        latitud           altitud     
 Min.   :0    Min.   :35.28   Min.   :-6.9492   Min.   :  1.0  
 1st Qu.:0    1st Qu.:37.42   1st Qu.:-4.4881   1st Qu.: 21.0  
 Median :0    Median :39.49   Median : 0.3664   Median : 68.6  
 Mean   :0    Mean   :39.42   Mean   :-1.0363   Mean   :130.2  
 3rd Qu.:0    3rd Qu.:41.48   3rd Qu.: 1.1789   3rd Qu.:185.0  
 Max.   :0    Max.   :43.36   Max.   : 4.2156   Max.   :953.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :165.0   Min.   : 54.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:231.0   1st Qu.:117.0   1st Qu.:  2.00   1st Qu.:0  
 Median : 7.000   Median :259.0   Median :136.0   Median :  8.00   Median :0  
 Mean   : 7.425   Mean   :263.6   Mean   :137.2   Mean   : 13.15   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:294.0   3rd Qu.:155.0   3rd Qu.: 18.00   3rd Qu.:0  
 Max.   :11.000   Max.   :400.0   Max.   :250.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :37.13   Min.   :-8.649   Min.   :   4.0  
 1st Qu.: 0.00000   1st Qu.:40.41   1st Qu.:-5.649   1st Qu.: 251.0  
 Median : 0.00000   Median :41.65   Median :-3.799   Median : 611.0  
 Mean   : 0.00578   Mean   :41.48   Mean   :-4.081   Mean   : 542.6  
 3rd Qu.: 0.00000   3rd Qu.:42.89   3rd Qu.:-2.483   3rd Qu.: 779.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 2.418   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.569   Mean   : 87.06   Mean   :  16.29   Mean   : 34.19  
 3rd Qu.:10.000   3rd Qu.:142.00   3rd Qu.:  65.00   3rd Qu.: 46.75  
 Max.   :12.000   Max.   :255.00   Max.   : 146.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.81   Mean   :41.93   Mean   :-0.2669   Mean   :2102  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:129.0   1st Qu.:  40.00   1st Qu.:  6.00  
 Median :11.00   Median :165.0   Median :  73.00   Median : 15.00  
 Mean   :10.98   Mean   :164.3   Mean   :  71.25   Mean   : 21.76  
 3rd Qu.:12.00   3rd Qu.:199.0   3rd Qu.: 101.00   3rd Qu.: 30.00  
 Max.   :12.00   Max.   :284.0   Max.   : 188.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.96   Median :-2.4544  
 Mean   :0.0004325   Mean   : 0.04792   Mean   :40.54   Mean   :-2.3602  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 261.0  
 Mean   : 376.6  
 3rd Qu.: 667.0  
 Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt         tmax            tmin           precip           nevada 
 Min.   :1.00   Min.   :100.0   Min.   :-12.0   Min.   :  0.00   Min.   :0  
 1st Qu.:2.00   1st Qu.:168.0   1st Qu.: 76.0   1st Qu.:  3.00   1st Qu.:0  
 Median :3.00   Median :193.0   Median :100.0   Median : 11.00   Median :0  
 Mean   :3.23   Mean   :198.3   Mean   :100.6   Mean   : 15.42   Mean   :0  
 3rd Qu.:5.00   3rd Qu.:225.0   3rd Qu.:125.0   3rd Qu.: 22.00   3rd Qu.:0  
 Max.   :8.00   Max.   :307.0   Max.   :191.0   Max.   :259.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.00  
 1st Qu.: 0.00000   1st Qu.:36.50   1st Qu.:-6.257   1st Qu.: 21.00  
 Median : 0.00000   Median :36.85   Median :-5.600   Median : 34.00  
 Mean   : 0.02453   Mean   :36.98   Mean   :-5.161   Mean   : 94.29  
 3rd Qu.: 0.00000   3rd Qu.:37.42   3rd Qu.:-4.488   3rd Qu.: 90.00  
 Max.   :34.00000   Max.   :39.47   Max.   :-0.500   Max.   :582.00  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : 69.0   Min.   :-41.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:154.0   1st Qu.: 52.00   1st Qu.:  4.00  
 Median :3.000   Median :180.0   Median : 77.00   Median :  9.00  
 Mean   :3.088   Mean   :181.5   Mean   : 77.63   Mean   : 13.23  
 3rd Qu.:4.000   3rd Qu.:209.0   3rd Qu.:103.00   3rd Qu.: 18.00  
 Max.   :6.000   Max.   :300.0   Max.   :178.00   Max.   :135.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.79   Min.   :-2.3308  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.: 0.4731  
 Median :0.0000000   Median : 0.00000   Median :41.15   Median : 0.7403  
 Mean   :0.0003687   Mean   : 0.02277   Mean   :40.45   Mean   : 1.0651  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.: 2.0792  
 Max.   :2.0000000   Max.   :40.00000   Max.   :43.36   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 14.0  
 Median : 71.0  
 Mean   :125.5  
 3rd Qu.:191.0  
 Max.   :816.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:111.0   1st Qu.: 15.00   1st Qu.:  7.00  
 Median :3.000   Median :141.0   Median : 43.00   Median : 16.00  
 Mean   :2.879   Mean   :140.7   Mean   : 41.42   Mean   : 21.44  
 3rd Qu.:4.000   3rd Qu.:170.0   3rd Qu.: 68.75   3rd Qu.: 29.00  
 Max.   :6.000   Max.   :256.0   Max.   :138.00   Max.   :371.00  
     nevada           prof_nieve         longitud        latitud      
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.66   1st Qu.:-5.649  
 Median :0.000000   Median : 0.0000   Median :41.99   Median :-3.789  
 Mean   :0.000829   Mean   : 0.1491   Mean   :41.71   Mean   :-3.770  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:42.87   3rd Qu.:-2.039  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 263.0  
 Median : 617.0  
 Mean   : 563.3  
 3rd Qu.: 790.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 5.000   Min.   :210.0   Min.   :105.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:272.0   1st Qu.:163.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :290.0   Median :181.0   Median :  3.000   Median :0  
 Mean   : 7.578   Mean   :292.5   Mean   :180.4   Mean   :  8.005   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:311.0   3rd Qu.:198.0   3rd Qu.: 11.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve    longitud        latitud           altitud     
 Min.   :0    Min.   :35.28   Min.   :-6.9492   Min.   :  1.0  
 1st Qu.:0    1st Qu.:37.42   1st Qu.:-4.4881   1st Qu.: 21.0  
 Median :0    Median :39.49   Median : 0.3664   Median : 68.6  
 Mean   :0    Mean   :39.42   Mean   :-1.0363   Mean   :130.2  
 3rd Qu.:0    3rd Qu.:41.48   3rd Qu.: 1.1789   3rd Qu.:185.0  
 Max.   :0    Max.   :43.36   Max.   : 4.2156   Max.   :953.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :165.0   Min.   : 54.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:231.0   1st Qu.:117.0   1st Qu.:  2.00   1st Qu.:0  
 Median : 7.000   Median :259.0   Median :136.0   Median :  8.00   Median :0  
 Mean   : 7.425   Mean   :263.6   Mean   :137.2   Mean   : 13.15   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:294.0   3rd Qu.:155.0   3rd Qu.: 18.00   3rd Qu.:0  
 Max.   :11.000   Max.   :400.0   Max.   :250.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :37.13   Min.   :-8.649   Min.   :   4.0  
 1st Qu.: 0.00000   1st Qu.:40.41   1st Qu.:-5.649   1st Qu.: 251.0  
 Median : 0.00000   Median :41.65   Median :-3.799   Median : 611.0  
 Mean   : 0.00578   Mean   :41.48   Mean   :-4.081   Mean   : 542.6  
 3rd Qu.: 0.00000   3rd Qu.:42.89   3rd Qu.:-2.483   3rd Qu.: 779.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 2.418   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.569   Mean   : 87.06   Mean   :  16.29   Mean   : 34.19  
 3rd Qu.:10.000   3rd Qu.:142.00   3rd Qu.:  65.00   3rd Qu.: 46.75  
 Max.   :12.000   Max.   :255.00   Max.   : 146.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.81   Mean   :41.93   Mean   :-0.2669   Mean   :2102  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:110.0   1st Qu.:  22.00   1st Qu.:  7.00  
 Median :11.00   Median :140.0   Median :  53.00   Median : 16.00  
 Mean   :10.97   Mean   :144.7   Mean   :  51.05   Mean   : 23.24  
 3rd Qu.:12.00   3rd Qu.:180.0   3rd Qu.:  82.00   3rd Qu.: 31.00  
 Max.   :12.00   Max.   :268.0   Max.   : 140.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud      
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.18   Min.   :-8.649  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:40.48   1st Qu.:-5.642  
 Median :0.0000000   Median : 0.00000   Median :41.66   Median :-3.789  
 Mean   :0.0006412   Mean   : 0.06458   Mean   :41.48   Mean   :-3.714  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.59   3rd Qu.:-2.039  
 Max.   :3.0000000   Max.   :40.00000   Max.   :43.57   Max.   : 2.418  
    altitud      
 Min.   :   4.0  
 1st Qu.: 442.0  
 Median : 656.0  
 Mean   : 612.6  
 3rd Qu.: 846.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt       tmax          tmin            precip      
 Min.   : 8   Min.   : 64   Min.   :-29.00   Min.   :  0.00  
 1st Qu.:10   1st Qu.:158   1st Qu.: 65.00   1st Qu.:  4.00  
 Median :11   Median :184   Median : 94.00   Median : 13.00  
 Mean   :11   Mean   :186   Mean   : 93.55   Mean   : 20.13  
 3rd Qu.:12   3rd Qu.:217   3rd Qu.:123.00   3rd Qu.: 28.00  
 Max.   :12   Max.   :284   Max.   :188.00   Max.   :206.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:37.79   1st Qu.:-3.7881  
 Median :0.0000000   Median : 0.00000   Median :39.56   Median : 0.4731  
 Mean   :0.0002022   Mean   : 0.02952   Mean   :39.50   Mean   :-0.8655  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.42   3rd Qu.: 1.3842  
 Max.   :2.0000000   Max.   :59.00000   Max.   :43.36   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 19.0  
 Median : 68.6  
 Mean   :116.0  
 3rd Qu.:176.0  
 Max.   :816.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)